]>
Commit | Line | Data |
---|---|---|
fc287219 | 1 | import re |
fc287219 | 2 | |
0af25f78 | 3 | from .common import InfoExtractor |
1cc79574 | 4 | from ..compat import ( |
e525d9a3 | 5 | compat_str, |
1cc79574 PH |
6 | ) |
7 | from ..utils import ( | |
fc287219 | 8 | ExtractorError, |
90834c78 | 9 | find_xpath_attr, |
5aafe895 | 10 | fix_xml_ampersands, |
8765151c | 11 | float_or_none, |
0ef68e04 | 12 | HEADRequest, |
605b684c | 13 | int_or_none, |
34921b43 | 14 | join_nonempty, |
0c75abbb | 15 | RegexNotFoundError, |
5c2266df | 16 | sanitized_Request, |
7cdfc4c9 | 17 | strip_or_none, |
712c7530 | 18 | timeconvert, |
adf063da | 19 | try_get, |
340b0468 | 20 | unescapeHTML, |
0c75abbb | 21 | update_url_query, |
8d9453b9 | 22 | url_basename, |
5767b4ee | 23 | xpath_text, |
fc287219 PH |
24 | ) |
25 | ||
90834c78 | 26 | |
300fcad8 JMF |
27 | def _media_xml_tag(tag): |
28 | return '{http://search.yahoo.com/mrss/}%s' % tag | |
fc287219 | 29 | |
f7e02595 | 30 | |
0af25f78 | 31 | class MTVServicesInfoExtractor(InfoExtractor): |
340b0468 | 32 | _MOBILE_TEMPLATE = None |
a542e372 | 33 | _LANG = None |
8940c1c0 | 34 | |
f7e02595 JMF |
35 | @staticmethod |
36 | def _id_from_uri(uri): | |
37 | return uri.split(':')[-1] | |
38 | ||
0c75abbb YCH |
39 | @staticmethod |
40 | def _remove_template_parameter(url): | |
41 | # Remove the templates, like &device={device} | |
42 | return re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', url) | |
43 | ||
02def271 | 44 | def _get_feed_url(self, uri, url=None): |
8940c1c0 JMF |
45 | return self._FEED_URL |
46 | ||
ab2f744b | 47 | def _get_thumbnail_url(self, uri, itemdoc): |
84db8181 JMF |
48 | search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail')) |
49 | thumb_node = itemdoc.find(search_path) | |
50 | if thumb_node is None: | |
51 | return None | |
70bfab0e | 52 | return thumb_node.get('url') or thumb_node.text or None |
f7e02595 | 53 | |
340b0468 JMF |
54 | def _extract_mobile_video_formats(self, mtvn_id): |
55 | webpage_url = self._MOBILE_TEMPLATE % mtvn_id | |
5c2266df | 56 | req = sanitized_Request(webpage_url) |
340b0468 | 57 | # Otherwise we get a webpage that would execute some javascript |
3fcfb8e9 | 58 | req.add_header('User-Agent', 'curl/7') |
340b0468 | 59 | webpage = self._download_webpage(req, mtvn_id, |
9e1a5b84 | 60 | 'Downloading mobile page') |
0ef68e04 JMF |
61 | metrics_url = unescapeHTML(self._search_regex(r'<a href="(http://metrics.+?)"', webpage, 'url')) |
62 | req = HEADRequest(metrics_url) | |
63 | response = self._request_webpage(req, mtvn_id, 'Resolving url') | |
64 | url = response.geturl() | |
65 | # Transform the url to get the best quality: | |
66 | url = re.sub(r'.+pxE=mp4', 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=0+_pxK=18639+_pxE=mp4', url, 1) | |
5f6a1245 | 67 | return [{'url': url, 'ext': 'mp4'}] |
340b0468 | 68 | |
dbaf6016 | 69 | def _extract_video_formats(self, mdoc, mtvn_id, video_id): |
054d43bb | 70 | if re.match(r'.*/(error_country_block\.swf|geoblock\.mp4|copyright_error\.flv(?:\?geo\b.+?)?)$', mdoc.find('.//src').text) is not None: |
340b0468 | 71 | if mtvn_id is not None and self._MOBILE_TEMPLATE is not None: |
0ef68e04 | 72 | self.to_screen('The normal version is not available from your ' |
9e1a5b84 | 73 | 'country, trying with the mobile version') |
340b0468 | 74 | return self._extract_mobile_video_formats(mtvn_id) |
cc1db7f9 | 75 | raise ExtractorError('This video is not available from your country.', |
9e1a5b84 | 76 | expected=True) |
f7e02595 | 77 | |
f13d0933 PH |
78 | formats = [] |
79 | for rendition in mdoc.findall('.//rendition'): | |
20faad74 | 80 | if rendition.get('method') == 'hls': |
dbaf6016 | 81 | hls_url = rendition.find('./src').text |
cdd11c05 | 82 | formats.extend(self._extract_m3u8_formats( |
adf063da | 83 | hls_url, video_id, ext='mp4', entry_protocol='m3u8_native', |
e0f1fb0a | 84 | m3u8_id='hls', fatal=False)) |
dbaf6016 PH |
85 | else: |
86 | # fms | |
87 | try: | |
88 | _, _, ext = rendition.attrib['type'].partition('/') | |
89 | rtmp_video_url = rendition.find('./src').text | |
adf063da S |
90 | if 'error_not_available.swf' in rtmp_video_url: |
91 | raise ExtractorError( | |
92 | '%s said: video is not available' % self.IE_NAME, | |
93 | expected=True) | |
dbaf6016 PH |
94 | if rtmp_video_url.endswith('siteunavail.png'): |
95 | continue | |
dbaf6016 | 96 | formats.extend([{ |
adf063da S |
97 | 'ext': 'flv' if rtmp_video_url.startswith('rtmp') else ext, |
98 | 'url': rtmp_video_url, | |
34921b43 | 99 | 'format_id': join_nonempty( |
adf063da | 100 | 'rtmp' if rtmp_video_url.startswith('rtmp') else None, |
34921b43 | 101 | rendition.get('bitrate')), |
dbaf6016 PH |
102 | 'width': int(rendition.get('width')), |
103 | 'height': int(rendition.get('height')), | |
adf063da | 104 | }]) |
dbaf6016 PH |
105 | except (KeyError, TypeError): |
106 | raise ExtractorError('Invalid rendition field.') | |
e0f1fb0a S |
107 | if formats: |
108 | self._sort_formats(formats) | |
f13d0933 | 109 | return formats |
f7e02595 | 110 | |
e525d9a3 S |
111 | def _extract_subtitles(self, mdoc, mtvn_id): |
112 | subtitles = {} | |
e525d9a3 S |
113 | for transcript in mdoc.findall('.//transcript'): |
114 | if transcript.get('kind') != 'captions': | |
115 | continue | |
116 | lang = transcript.get('srclang') | |
5ea765fb RA |
117 | for typographic in transcript.findall('./typographic'): |
118 | sub_src = typographic.get('src') | |
119 | if not sub_src: | |
120 | continue | |
121 | ext = typographic.get('format') | |
122 | if ext == 'cea-608': | |
123 | ext = 'scc' | |
124 | subtitles.setdefault(lang, []).append({ | |
125 | 'url': compat_str(sub_src), | |
126 | 'ext': ext | |
127 | }) | |
0af25f78 | 128 | return subtitles |
e525d9a3 | 129 | |
67fc365b | 130 | def _get_video_info(self, itemdoc, use_hls=True): |
f7e02595 JMF |
131 | uri = itemdoc.find('guid').text |
132 | video_id = self._id_from_uri(uri) | |
133 | self.report_extraction(video_id) | |
04cbc498 | 134 | content_el = itemdoc.find('%s/%s' % (_media_xml_tag('group'), _media_xml_tag('content'))) |
0c75abbb | 135 | mediagen_url = self._remove_template_parameter(content_el.attrib['url']) |
dbaf6016 | 136 | mediagen_url = mediagen_url.replace('device={device}', '') |
f7e02595 | 137 | if 'acceptMethods' not in mediagen_url: |
56f447be | 138 | mediagen_url += '&' if '?' in mediagen_url else '?' |
dbaf6016 PH |
139 | mediagen_url += 'acceptMethods=' |
140 | mediagen_url += 'hls' if use_hls else 'fms' | |
6562df76 | 141 | |
e0f1fb0a S |
142 | mediagen_doc = self._download_xml( |
143 | mediagen_url, video_id, 'Downloading video urls', fatal=False) | |
144 | ||
145 | if mediagen_doc is False: | |
146 | return None | |
f7e02595 | 147 | |
0dfe9bc9 S |
148 | item = mediagen_doc.find('./video/item') |
149 | if item is not None and item.get('type') == 'text': | |
150 | message = '%s returned error: ' % self.IE_NAME | |
151 | if item.get('code') is not None: | |
152 | message += '%s - ' % item.get('code') | |
153 | message += item.text | |
154 | raise ExtractorError(message, expected=True) | |
155 | ||
7cdfc4c9 | 156 | description = strip_or_none(xpath_text(itemdoc, 'description')) |
f13d0933 | 157 | |
712c7530 YCH |
158 | timestamp = timeconvert(xpath_text(itemdoc, 'pubDate')) |
159 | ||
90834c78 PH |
160 | title_el = None |
161 | if title_el is None: | |
162 | title_el = find_xpath_attr( | |
163 | itemdoc, './/{http://search.yahoo.com/mrss/}category', | |
164 | 'scheme', 'urn:mtvn:video_title') | |
90834c78 | 165 | if title_el is None: |
f9934b96 | 166 | title_el = itemdoc.find('.//{http://search.yahoo.com/mrss/}title') |
96cb10a5 | 167 | if title_el is None: |
f9934b96 | 168 | title_el = itemdoc.find('.//title') |
1df4229b PH |
169 | if title_el.text is None: |
170 | title_el = None | |
1df4229b | 171 | |
90834c78 PH |
172 | title = title_el.text |
173 | if title is None: | |
174 | raise ExtractorError('Could not find video title') | |
780ee4e5 | 175 | title = title.strip() |
90834c78 | 176 | |
605b684c | 177 | series = find_xpath_attr( |
178 | itemdoc, './/{http://search.yahoo.com/mrss/}category', | |
179 | 'scheme', 'urn:mtvn:franchise') | |
180 | season = find_xpath_attr( | |
181 | itemdoc, './/{http://search.yahoo.com/mrss/}category', | |
182 | 'scheme', 'urn:mtvn:seasonN') | |
183 | episode = find_xpath_attr( | |
184 | itemdoc, './/{http://search.yahoo.com/mrss/}category', | |
185 | 'scheme', 'urn:mtvn:episodeN') | |
186 | series = series.text if series is not None else None | |
187 | season = season.text if season is not None else None | |
188 | episode = episode.text if episode is not None else None | |
189 | if season and episode: | |
190 | # episode number includes season, so remove it | |
191 | episode = re.sub(r'^%s' % season, '', episode) | |
192 | ||
340b0468 JMF |
193 | # This a short id that's used in the webpage urls |
194 | mtvn_id = None | |
195 | mtvn_id_node = find_xpath_attr(itemdoc, './/{http://search.yahoo.com/mrss/}category', | |
9e1a5b84 | 196 | 'scheme', 'urn:mtvn:id') |
340b0468 JMF |
197 | if mtvn_id_node is not None: |
198 | mtvn_id = mtvn_id_node.text | |
199 | ||
dbaf6016 PH |
200 | formats = self._extract_video_formats(mediagen_doc, mtvn_id, video_id) |
201 | ||
e0f1fb0a S |
202 | # Some parts of complete video may be missing (e.g. missing Act 3 in |
203 | # http://www.southpark.de/alle-episoden/s14e01-sexual-healing) | |
204 | if not formats: | |
205 | return None | |
206 | ||
207 | self._sort_formats(formats) | |
208 | ||
fb7abb31 | 209 | return { |
90834c78 | 210 | 'title': title, |
dbaf6016 | 211 | 'formats': formats, |
e525d9a3 | 212 | 'subtitles': self._extract_subtitles(mediagen_doc, mtvn_id), |
f13d0933 PH |
213 | 'id': video_id, |
214 | 'thumbnail': self._get_thumbnail_url(uri, itemdoc), | |
215 | 'description': description, | |
04cbc498 | 216 | 'duration': float_or_none(content_el.attrib.get('duration')), |
712c7530 | 217 | 'timestamp': timestamp, |
605b684c | 218 | 'series': series, |
219 | 'season_number': int_or_none(season), | |
220 | 'episode_number': int_or_none(episode), | |
f13d0933 PH |
221 | } |
222 | ||
c1e90619 | 223 | def _get_feed_query(self, uri): |
224 | data = {'uri': uri} | |
225 | if self._LANG: | |
226 | data['lang'] = self._LANG | |
0c75abbb | 227 | return data |
c1e90619 | 228 | |
02def271 | 229 | def _get_videos_info(self, uri, use_hls=True, url=None): |
f7e02595 | 230 | video_id = self._id_from_uri(uri) |
02def271 | 231 | feed_url = self._get_feed_url(uri, url) |
0c75abbb | 232 | info_url = update_url_query(feed_url, self._get_feed_query(uri)) |
dbaf6016 | 233 | return self._get_videos_info_from_url(info_url, video_id, use_hls) |
79fa9db0 | 234 | |
67fc365b | 235 | def _get_videos_info_from_url(self, url, video_id, use_hls=True): |
e2b38da9 | 236 | idoc = self._download_xml( |
79fa9db0 | 237 | url, video_id, |
32dac694 | 238 | 'Downloading info', transform_source=fix_xml_ampersands) |
712c7530 YCH |
239 | |
240 | title = xpath_text(idoc, './channel/title') | |
241 | description = xpath_text(idoc, './channel/description') | |
242 | ||
e0f1fb0a S |
243 | entries = [] |
244 | for item in idoc.findall('.//item'): | |
245 | info = self._get_video_info(item, use_hls) | |
246 | if info: | |
247 | entries.append(info) | |
248 | ||
bc97cdae | 249 | # TODO: should be multi-video |
5239075b | 250 | return self.playlist_result( |
e0f1fb0a | 251 | entries, playlist_title=title, playlist_description=description) |
fc287219 | 252 | |
adf063da S |
253 | def _extract_triforce_mgid(self, webpage, data_zone=None, video_id=None): |
254 | triforce_feed = self._parse_json(self._search_regex( | |
f1e70fc2 | 255 | r'triforceManifestFeed\s*=\s*({.+?})\s*;\s*\n', webpage, |
adf063da S |
256 | 'triforce feed', default='{}'), video_id, fatal=False) |
257 | ||
258 | data_zone = self._search_regex( | |
259 | r'data-zone=(["\'])(?P<zone>.+?_lc_promo.*?)\1', webpage, | |
260 | 'data zone', default=data_zone, group='zone') | |
261 | ||
262 | feed_url = try_get( | |
263 | triforce_feed, lambda x: x['manifest']['zones'][data_zone]['feed'], | |
264 | compat_str) | |
265 | if not feed_url: | |
266 | return | |
267 | ||
268 | feed = self._download_json(feed_url, video_id, fatal=False) | |
269 | if not feed: | |
270 | return | |
271 | ||
272 | return try_get(feed, lambda x: x['result']['data']['id'], compat_str) | |
273 | ||
a820dc72 RA |
274 | @staticmethod |
275 | def _extract_child_with_type(parent, t): | |
f7ad7160 | 276 | for c in parent['children']: |
277 | if c.get('type') == t: | |
278 | return c | |
a820dc72 | 279 | |
ee1e0558 | 280 | def _extract_mgid(self, webpage): |
8d9453b9 | 281 | try: |
4bbf139a JMF |
282 | # the url can be http://media.mtvnservices.com/fb/{mgid}.swf |
283 | # or http://media.mtvnservices.com/{mgid} | |
284 | og_url = self._og_search_video_url(webpage) | |
285 | mgid = url_basename(og_url) | |
286 | if mgid.endswith('.swf'): | |
287 | mgid = mgid[:-4] | |
8d9453b9 | 288 | except RegexNotFoundError: |
b1298d8e AMW |
289 | mgid = None |
290 | ||
291 | if mgid is None or ':' not in mgid: | |
b9381e43 | 292 | mgid = self._search_regex( |
197224b7 | 293 | [r'data-mgid="(.*?)"', r'swfobject\.embedSWF\(".*?(mgid:.*?)"'], |
fc42bc6e S |
294 | webpage, 'mgid', default=None) |
295 | ||
296 | if not mgid: | |
297 | sm4_embed = self._html_search_meta( | |
298 | 'sm4:video:embed', webpage, 'sm4 embed', default='') | |
299 | mgid = self._search_regex( | |
adf063da S |
300 | r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid', default=None) |
301 | ||
b6e0c7d2 | 302 | if not mgid: |
ee1e0558 | 303 | mgid = self._extract_triforce_mgid(webpage) |
adf063da | 304 | |
a820dc72 RA |
305 | if not mgid: |
306 | data = self._parse_json(self._search_regex( | |
307 | r'__DATA__\s*=\s*({.+?});', webpage, 'data'), None) | |
308 | main_container = self._extract_child_with_type(data, 'MainContainer') | |
f7ad7160 | 309 | ab_testing = self._extract_child_with_type(main_container, 'ABTesting') |
310 | video_player = self._extract_child_with_type(ab_testing or main_container, 'VideoPlayer') | |
fec41d17 S |
311 | if video_player: |
312 | mgid = try_get(video_player, lambda x: x['props']['media']['video']['config']['uri']) | |
313 | else: | |
314 | flex_wrapper = self._extract_child_with_type(ab_testing or main_container, 'FlexWrapper') | |
315 | auth_suite_wrapper = self._extract_child_with_type(flex_wrapper, 'AuthSuiteWrapper') | |
316 | player = self._extract_child_with_type(auth_suite_wrapper or flex_wrapper, 'Player') | |
317 | if player: | |
318 | mgid = try_get(player, lambda x: x['props']['videoDetail']['mgid']) | |
319 | ||
320 | if not mgid: | |
321 | raise ExtractorError('Could not extract mgid') | |
a820dc72 | 322 | |
c1e90619 | 323 | return mgid |
e525d9a3 | 324 | |
c1e90619 | 325 | def _real_extract(self, url): |
326 | title = url_basename(url) | |
327 | webpage = self._download_webpage(url, title) | |
ee1e0558 | 328 | mgid = self._extract_mgid(webpage) |
02def271 | 329 | videos_info = self._get_videos_info(mgid, url=url) |
e525d9a3 | 330 | return videos_info |
8d9453b9 | 331 | |
84db8181 | 332 | |
8940c1c0 JMF |
333 | class MTVServicesEmbeddedIE(MTVServicesInfoExtractor): |
334 | IE_NAME = 'mtvservices:embedded' | |
335 | _VALID_URL = r'https?://media\.mtvnservices\.com/embed/(?P<mgid>.+?)(\?|/|$)' | |
336 | ||
337 | _TEST = { | |
338 | # From http://www.thewrap.com/peter-dinklage-sums-up-game-of-thrones-in-45-seconds-video/ | |
339 | 'url': 'http://media.mtvnservices.com/embed/mgid:uma:video:mtv.com:1043906/cp~vid%3D1043906%26uri%3Dmgid%3Auma%3Avideo%3Amtv.com%3A1043906', | |
340 | 'md5': 'cb349b21a7897164cede95bd7bf3fbb9', | |
341 | 'info_dict': { | |
342 | 'id': '1043906', | |
343 | 'ext': 'mp4', | |
344 | 'title': 'Peter Dinklage Sums Up \'Game Of Thrones\' In 45 Seconds', | |
345 | 'description': '"Sexy sexy sexy, stabby stabby stabby, beautiful language," says Peter Dinklage as he tries summarizing "Game of Thrones" in under a minute.', | |
712c7530 YCH |
346 | 'timestamp': 1400126400, |
347 | 'upload_date': '20140515', | |
8940c1c0 JMF |
348 | }, |
349 | } | |
350 | ||
fe1d858e S |
351 | @staticmethod |
352 | def _extract_url(webpage): | |
353 | mobj = re.search( | |
1418a043 | 354 | r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//media\.mtvnservices\.com/embed/.+?)\1', webpage) |
fe1d858e S |
355 | if mobj: |
356 | return mobj.group('url') | |
357 | ||
02def271 | 358 | def _get_feed_url(self, uri, url=None): |
8940c1c0 | 359 | video_id = self._id_from_uri(uri) |
0c75abbb YCH |
360 | config = self._download_json( |
361 | 'http://media.mtvnservices.com/pmt/e1/access/index.html?uri=%s&configtype=edge' % uri, video_id) | |
362 | return self._remove_template_parameter(config['feedWithQueryParams']) | |
8940c1c0 JMF |
363 | |
364 | def _real_extract(self, url): | |
5ad28e7f | 365 | mobj = self._match_valid_url(url) |
8940c1c0 JMF |
366 | mgid = mobj.group('mgid') |
367 | return self._get_videos_info(mgid) | |
368 | ||
369 | ||
84db8181 | 370 | class MTVIE(MTVServicesInfoExtractor): |
a54ffb8a | 371 | IE_NAME = 'mtv' |
cf0cabbe | 372 | _VALID_URL = r'https?://(?:www\.)?mtv\.com/(?:video-clips|(?:full-)?episodes)/(?P<id>[^/?#.]+)' |
8add4bfe RA |
373 | _FEED_URL = 'http://www.mtv.com/feeds/mrss/' |
374 | ||
375 | _TESTS = [{ | |
376 | 'url': 'http://www.mtv.com/video-clips/vl8qof/unlocking-the-truth-trailer', | |
377 | 'md5': '1edbcdf1e7628e414a8c5dcebca3d32b', | |
378 | 'info_dict': { | |
379 | 'id': '5e14040d-18a4-47c4-a582-43ff602de88e', | |
380 | 'ext': 'mp4', | |
381 | 'title': 'Unlocking The Truth|July 18, 2016|1|101|Trailer', | |
382 | 'description': '"Unlocking the Truth" premieres August 17th at 11/10c.', | |
383 | 'timestamp': 1468846800, | |
384 | 'upload_date': '20160718', | |
385 | }, | |
386 | }, { | |
387 | 'url': 'http://www.mtv.com/full-episodes/94tujl/unlocking-the-truth-gates-of-hell-season-1-ep-101', | |
388 | 'only_matching': True, | |
cf0cabbe S |
389 | }, { |
390 | 'url': 'http://www.mtv.com/episodes/g8xu7q/teen-mom-2-breaking-the-wall-season-7-ep-713', | |
391 | 'only_matching': True, | |
8add4bfe RA |
392 | }] |
393 | ||
394 | ||
3cdcebf5 RA |
395 | class MTVJapanIE(MTVServicesInfoExtractor): |
396 | IE_NAME = 'mtvjapan' | |
397 | _VALID_URL = r'https?://(?:www\.)?mtvjapan\.com/videos/(?P<id>[0-9a-z]+)' | |
008f2470 S |
398 | |
399 | _TEST = { | |
3cdcebf5 | 400 | 'url': 'http://www.mtvjapan.com/videos/prayht/fresh-info-cadillac-escalade', |
008f2470 | 401 | 'info_dict': { |
3cdcebf5 | 402 | 'id': 'bc01da03-6fe5-4284-8880-f291f4e368f5', |
008f2470 | 403 | 'ext': 'mp4', |
3cdcebf5 RA |
404 | 'title': '【Fresh Info】Cadillac ESCALADE Sport Edition', |
405 | }, | |
406 | 'params': { | |
407 | 'skip_download': True, | |
008f2470 S |
408 | }, |
409 | } | |
3cdcebf5 RA |
410 | _GEO_COUNTRIES = ['JP'] |
411 | _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed' | |
008f2470 | 412 | |
3cdcebf5 RA |
413 | def _get_feed_query(self, uri): |
414 | return { | |
415 | 'arcEp': 'mtvjapan.com', | |
416 | 'mgid': uri, | |
417 | } | |
008f2470 S |
418 | |
419 | ||
8add4bfe | 420 | class MTVVideoIE(MTVServicesInfoExtractor): |
a54ffb8a | 421 | IE_NAME = 'mtv:video' |
5c541b2c JMF |
422 | _VALID_URL = r'''(?x)^https?:// |
423 | (?:(?:www\.)?mtv\.com/videos/.+?/(?P<videoid>[0-9]+)/[^/]+$| | |
424 | m\.mtv\.com/videos/video\.rbml\?.*?id=(?P<mgid>[^&]+))''' | |
84db8181 JMF |
425 | |
426 | _FEED_URL = 'http://www.mtv.com/player/embed/AS3/rss/' | |
427 | ||
428 | _TESTS = [ | |
429 | { | |
32dac694 | 430 | 'url': 'http://www.mtv.com/videos/misc/853555/ours-vh1-storytellers.jhtml', |
32dac694 PH |
431 | 'md5': '850f3f143316b1e71fa56a4edfd6e0f8', |
432 | 'info_dict': { | |
ca0f500e PH |
433 | 'id': '853555', |
434 | 'ext': 'mp4', | |
32dac694 PH |
435 | 'title': 'Taylor Swift - "Ours (VH1 Storytellers)"', |
436 | 'description': 'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.', | |
712c7530 YCH |
437 | 'timestamp': 1352610000, |
438 | 'upload_date': '20121111', | |
84db8181 JMF |
439 | }, |
440 | }, | |
84db8181 JMF |
441 | ] |
442 | ||
443 | def _get_thumbnail_url(self, uri, itemdoc): | |
444 | return 'http://mtv.mtvnimages.com/uri/' + uri | |
445 | ||
fc287219 | 446 | def _real_extract(self, url): |
5ad28e7f | 447 | mobj = self._match_valid_url(url) |
fc287219 | 448 | video_id = mobj.group('videoid') |
c801b205 | 449 | uri = mobj.groupdict().get('mgid') |
5c541b2c JMF |
450 | if uri is None: |
451 | webpage = self._download_webpage(url, video_id) | |
5f6a1245 | 452 | |
5c541b2c | 453 | # Some videos come from Vevo.com |
ca0f500e PH |
454 | m_vevo = re.search( |
455 | r'(?s)isVevoVideo = true;.*?vevoVideoId = "(.*?)";', webpage) | |
5c541b2c | 456 | if m_vevo: |
8bcc8756 | 457 | vevo_id = m_vevo.group(1) |
32dac694 | 458 | self.to_screen('Vevo video detected: %s' % vevo_id) |
5c541b2c | 459 | return self.url_result('vevo:%s' % vevo_id, ie='Vevo') |
5f6a1245 | 460 | |
32dac694 | 461 | uri = self._html_search_regex(r'/uri/(.*?)\?', webpage, 'uri') |
f7e02595 | 462 | return self._get_videos_info(uri) |
bc4ba05f JMF |
463 | |
464 | ||
071c1013 PH |
465 | class MTVDEIE(MTVServicesInfoExtractor): |
466 | IE_NAME = 'mtv.de' | |
cfabc505 | 467 | _VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:musik/videoclips|folgen|news)/(?P<id>[0-9a-z]+)' |
79fa9db0 | 468 | _TESTS = [{ |
cfabc505 | 469 | 'url': 'http://www.mtv.de/musik/videoclips/2gpnv7/Traum', |
79fa9db0 | 470 | 'info_dict': { |
cfabc505 RA |
471 | 'id': 'd5d472bc-f5b7-11e5-bffd-a4badb20dab5', |
472 | 'ext': 'mp4', | |
473 | 'title': 'Traum', | |
474 | 'description': 'Traum', | |
071c1013 | 475 | }, |
79fa9db0 S |
476 | 'params': { |
477 | # rtmp download | |
478 | 'skip_download': True, | |
479 | }, | |
35f6e0ff | 480 | 'skip': 'Blocked at Travis CI', |
c3c9f879 S |
481 | }, { |
482 | # mediagen URL without query (e.g. http://videos.mtvnn.com/mediagen/e865da714c166d18d6f80893195fcb97) | |
cfabc505 | 483 | 'url': 'http://www.mtv.de/folgen/6b1ylu/teen-mom-2-enthuellungen-S5-F1', |
c3c9f879 | 484 | 'info_dict': { |
cfabc505 RA |
485 | 'id': '1e5a878b-31c5-11e7-a442-0e40cf2fc285', |
486 | 'ext': 'mp4', | |
487 | 'title': 'Teen Mom 2', | |
488 | 'description': 'md5:dc65e357ef7e1085ed53e9e9d83146a7', | |
c3c9f879 S |
489 | }, |
490 | 'params': { | |
491 | # rtmp download | |
492 | 'skip_download': True, | |
493 | }, | |
35f6e0ff | 494 | 'skip': 'Blocked at Travis CI', |
65488b82 | 495 | }, { |
cfabc505 | 496 | 'url': 'http://www.mtv.de/news/glolix/77491-mtv-movies-spotlight--pixels--teil-3', |
65488b82 S |
497 | 'info_dict': { |
498 | 'id': 'local_playlist-4e760566473c4c8c5344', | |
499 | 'ext': 'mp4', | |
500 | 'title': 'Article_mtv-movies-spotlight-pixels-teil-3_short-clips_part1', | |
501 | 'description': 'MTV Movies Supercut', | |
502 | }, | |
503 | 'params': { | |
504 | # rtmp download | |
505 | 'skip_download': True, | |
506 | }, | |
712c7530 | 507 | 'skip': 'Das Video kann zur Zeit nicht abgespielt werden.', |
79fa9db0 | 508 | }] |
cfabc505 RA |
509 | _GEO_COUNTRIES = ['DE'] |
510 | _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed' | |
071c1013 | 511 | |
cfabc505 RA |
512 | def _get_feed_query(self, uri): |
513 | return { | |
514 | 'arcEp': 'mtv.de', | |
515 | 'mgid': uri, | |
516 | } | |
605b684c | 517 | |
518 | ||
519 | class MTVItaliaIE(MTVServicesInfoExtractor): | |
520 | IE_NAME = 'mtv.it' | |
521 | _VALID_URL = r'https?://(?:www\.)?mtv\.it/(?:episodi|video|musica)/(?P<id>[0-9a-z]+)' | |
522 | _TESTS = [{ | |
523 | 'url': 'http://www.mtv.it/episodi/24bqab/mario-una-serie-di-maccio-capatonda-cavoli-amario-episodio-completo-S1-E1', | |
524 | 'info_dict': { | |
525 | 'id': '0f0fc78e-45fc-4cce-8f24-971c25477530', | |
526 | 'ext': 'mp4', | |
527 | 'title': 'Cavoli amario (episodio completo)', | |
528 | 'description': 'md5:4962bccea8fed5b7c03b295ae1340660', | |
529 | 'series': 'Mario - Una Serie Di Maccio Capatonda', | |
530 | 'season_number': 1, | |
531 | 'episode_number': 1, | |
532 | }, | |
533 | 'params': { | |
534 | 'skip_download': True, | |
535 | }, | |
536 | }] | |
537 | _GEO_COUNTRIES = ['IT'] | |
538 | _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed' | |
539 | ||
540 | def _get_feed_query(self, uri): | |
541 | return { | |
542 | 'arcEp': 'mtv.it', | |
543 | 'mgid': uri, | |
544 | } | |
545 | ||
546 | ||
547 | class MTVItaliaProgrammaIE(MTVItaliaIE): | |
548 | IE_NAME = 'mtv.it:programma' | |
549 | _VALID_URL = r'https?://(?:www\.)?mtv\.it/(?:programmi|playlist)/(?P<id>[0-9a-z]+)' | |
550 | _TESTS = [{ | |
551 | # program page: general | |
552 | 'url': 'http://www.mtv.it/programmi/s2rppv/mario-una-serie-di-maccio-capatonda', | |
553 | 'info_dict': { | |
554 | 'id': 'a6f155bc-8220-4640-aa43-9b95f64ffa3d', | |
555 | 'title': 'Mario - Una Serie Di Maccio Capatonda', | |
556 | 'description': 'md5:72fbffe1f77ccf4e90757dd4e3216153', | |
557 | }, | |
558 | 'playlist_count': 2, | |
559 | 'params': { | |
560 | 'skip_download': True, | |
561 | }, | |
562 | }, { | |
563 | # program page: specific season | |
564 | 'url': 'http://www.mtv.it/programmi/d9ncjf/mario-una-serie-di-maccio-capatonda-S2', | |
565 | 'info_dict': { | |
566 | 'id': '4deeb5d8-f272-490c-bde2-ff8d261c6dd1', | |
567 | 'title': 'Mario - Una Serie Di Maccio Capatonda - Stagione 2', | |
568 | }, | |
569 | 'playlist_count': 34, | |
570 | 'params': { | |
571 | 'skip_download': True, | |
572 | }, | |
573 | }, { | |
574 | # playlist page + redirect | |
575 | 'url': 'http://www.mtv.it/playlist/sexy-videos/ilctal', | |
576 | 'info_dict': { | |
577 | 'id': 'dee8f9ee-756d-493b-bf37-16d1d2783359', | |
578 | 'title': 'Sexy Videos', | |
579 | }, | |
580 | 'playlist_mincount': 145, | |
581 | 'params': { | |
582 | 'skip_download': True, | |
583 | }, | |
584 | }] | |
585 | _GEO_COUNTRIES = ['IT'] | |
586 | _FEED_URL = 'http://www.mtv.it/feeds/triforce/manifest/v8' | |
587 | ||
588 | def _get_entries(self, title, url): | |
589 | while True: | |
590 | pg = self._search_regex(r'/(\d+)$', url, 'entries', '1') | |
591 | entries = self._download_json(url, title, 'page %s' % pg) | |
592 | url = try_get( | |
593 | entries, lambda x: x['result']['nextPageURL'], compat_str) | |
594 | entries = try_get( | |
595 | entries, ( | |
596 | lambda x: x['result']['data']['items'], | |
597 | lambda x: x['result']['data']['seasons']), | |
598 | list) | |
599 | for entry in entries or []: | |
600 | if entry.get('canonicalURL'): | |
601 | yield self.url_result(entry['canonicalURL']) | |
602 | if not url: | |
603 | break | |
604 | ||
605 | def _real_extract(self, url): | |
606 | query = {'url': url} | |
607 | info_url = update_url_query(self._FEED_URL, query) | |
608 | video_id = self._match_id(url) | |
609 | info = self._download_json(info_url, video_id).get('manifest') | |
610 | ||
611 | redirect = try_get( | |
612 | info, lambda x: x['newLocation']['url'], compat_str) | |
613 | if redirect: | |
614 | return self.url_result(redirect) | |
615 | ||
616 | title = info.get('title') | |
617 | video_id = try_get( | |
618 | info, lambda x: x['reporting']['itemId'], compat_str) | |
619 | parent_id = try_get( | |
620 | info, lambda x: x['reporting']['parentId'], compat_str) | |
621 | ||
622 | playlist_url = current_url = None | |
623 | for z in (info.get('zones') or {}).values(): | |
624 | if z.get('moduleName') in ('INTL_M304', 'INTL_M209'): | |
625 | info_url = z.get('feed') | |
626 | if z.get('moduleName') in ('INTL_M308', 'INTL_M317'): | |
627 | playlist_url = playlist_url or z.get('feed') | |
628 | if z.get('moduleName') in ('INTL_M300',): | |
629 | current_url = current_url or z.get('feed') | |
630 | ||
631 | if not info_url: | |
632 | raise ExtractorError('No info found') | |
633 | ||
634 | if video_id == parent_id: | |
635 | video_id = self._search_regex( | |
636 | r'([^\/]+)/[^\/]+$', info_url, 'video_id') | |
637 | ||
638 | info = self._download_json(info_url, video_id, 'Show infos') | |
639 | info = try_get(info, lambda x: x['result']['data'], dict) | |
640 | title = title or try_get( | |
641 | info, ( | |
642 | lambda x: x['title'], | |
643 | lambda x: x['headline']), | |
644 | compat_str) | |
645 | description = try_get(info, lambda x: x['content'], compat_str) | |
646 | ||
647 | if current_url: | |
648 | season = try_get( | |
649 | self._download_json(playlist_url, video_id, 'Seasons info'), | |
650 | lambda x: x['result']['data'], dict) | |
651 | current = try_get( | |
652 | season, lambda x: x['currentSeason'], compat_str) | |
653 | seasons = try_get( | |
654 | season, lambda x: x['seasons'], list) or [] | |
655 | ||
656 | if current in [s.get('eTitle') for s in seasons]: | |
657 | playlist_url = current_url | |
658 | ||
659 | title = re.sub( | |
660 | r'[-|]\s*(?:mtv\s*italia|programma|playlist)', | |
661 | '', title, flags=re.IGNORECASE).strip() | |
662 | ||
663 | return self.playlist_result( | |
664 | self._get_entries(title, playlist_url), | |
665 | video_id, title, description) |